PRIMENA TEHNIKA MAŠINSKOG UČENJA NA PROBLEM KLASIFIKACIJE RAZLIČITIH SCENARIJA BOTNET NAPADA

Luka Mladenović

doi:10.24867/32BE12Mladenovic

Elektrotehničko i računarsko inženjerstvo

God. 40 Br. 10 (2025): Zbornik radova Fakulteta tehničkih nauka

PRIMENA TEHNIKA MAŠINSKOG UČENJA NA PROBLEM KLASIFIKACIJE RAZLIČITIH SCENARIJA BOTNET NAPADA

Luka Mladenović

32BE12Mladenovic.pdf

DOI:: https://doi.org/10.24867/32BE12Mladenovic
Predato: October 19, 2025
Objavljeno: 2026-01-02

Apstrakt

Sajber napadi postaju deo svakodnevice, a sa učestalošću raste i njihova sofisticiranost. Upravo zato je potrebno više napretka i kontinuirane inovacije u odbrambenim strategijama. Tradicionalne metode otkrivanja upada i dubinske inspekcije paketa, iako se još uvek u velikoj meri koriste i preporučuju, više nisu dovoljne da zadovolje zahteve rastućih pretnji po bezbednost.

Reference

[1] Claise, Benoit. 2004. Cisco systems netflow services export version.
[2] Choras, Rafal Kozik and Michal. 2017. “Pattern Extraction Algorithm for NetFlow-Based Botnet Activities Detection". Security and Communication Networks 2017.
[3] Cynthia Wagner, Jerome Francois, Thomas Engel, et al. 2011. Machine learning approach for ip-flow record anomaly detection. International Conference on Research in Networking, Springer.
[4] Wikipedia. Accessed 09 01, 2024. https ://en .wikipedia .org/wiki/Machine_learning
[5] Matija Stevanovic, Jens Myrup Pedersen. 2014. "An efficient flow-based botnet detection using supervised machine learning." 2014 international conference on computing, networking and 797-801.
[6] David Santana, Shan Suthaharan, Somya Mohanty. 2018. "What we learn from learning-Understanding capabilities and limitations of machine learning in botnet attacks." arXiv preprint
[7] Kozik Rafal, Michal Choras, and Jorg Keller. 2019. "Balanced Efficient Lifelong Learning (B-ELLA)
[8] P Fruehwirt, S Schrittwieser, i ER Weippl. 2014. "Using machine learning techniques for traffic classification [9] Jiangpan Hou et. 2018. "Machine Learning Based DDos Detection Through NetFlow Analysis."

[1] [1] Claise, Benoit. 2004. Cisco systems netflow services export version.

[2] [2] Choras, Rafal Kozik and Michal. 2017. “Pattern Extraction Algorithm for NetFlow-Based Botnet Activities Detection". Security and Communication Networks 2017.

[3] [3] Cynthia Wagner, Jerome Francois, Thomas Engel, et al. 2011. Machine learning approach for ip-flow record anomaly detection. International Conference on Research in Networking, Springer.

[4] [4] Wikipedia. Accessed 09 01, 2024. https ://en .wikipedia .org/wiki/Machine_learning

[5] [5] Matija Stevanovic, Jens Myrup Pedersen. 2014. "An efficient flow-based botnet detection using supervised machine learning." 2014 international conference on computing, networking and 797-801.

[6] [6] David Santana, Shan Suthaharan, Somya Mohanty. 2018. "What we learn from learning-Understanding capabilities and limitations of machine learning in botnet attacks." arXiv preprint

[7] [7] Kozik Rafal, Michal Choras, and Jorg Keller. 2019. "Balanced Efficient Lifelong Learning (B-ELLA)

[8] [8] P Fruehwirt, S Schrittwieser, i ER Weippl. 2014. "Using machine learning techniques for traffic classification [9] Jiangpan Hou et. 2018. "Machine Learning Based DDos Detection Through NetFlow Analysis."